INDEX

Explanations

instances of the word "adopt" or variations of it in a context related to decision-making or acceptance

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OIL

-0.70

othal

-0.69

 istg

-0.65

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.64

isal

-0.63

imir

-0.63

selves

-0.63

 Templ

-0.61

zzi

-0.60

iere

-0.60

POSITIVE LOGITS

 adopt

0.82

 adopted

0.81

 Viper

0.78

 adoption

0.72

 adopting

0.69

mits

0.67

ively

0.66

irtual

0.66

ions

0.64

resses

0.62

Activations Density 10.799%

instances of the word "adopt" or variations of it in a context related to decision-making or acceptance

No Comments

No Known Activations